Канал: Deploying AI

Stream an Agent to a Copilot UI with Groq’s Fast Inference (Llama 3, Groq, LangGraph)

Stream an Agent to a Copilot UI with Groq’s Fast Inference (Llama 3, Groq, LangGraph)

Building Agents: Visualize a Multi-Agent Workflow that Outperforms a Single SOTA Prompt

Building Agents: Visualize a Multi-Agent Workflow that Outperforms a Single SOTA Prompt

Building Agents: Self-Improving Prompt Engineering Agent that Runs Evals and Iterates on a Prompt

Building Agents: Self-Improving Prompt Engineering Agent that Runs Evals and Iterates on a Prompt

Build an Agent with Long-Term, Personalized Memory

Build an Agent with Long-Term, Personalized Memory

Use the OpenAI API to call Mistral, Llama, and other LLMs (works with local AND serverless models)

Use the OpenAI API to call Mistral, Llama, and other LLMs (works with local AND serverless models)

LangGraph Deep Dive: Agents with Parallel Function Calling

LangGraph Deep Dive: Agents with Parallel Function Calling

Run Code Llama 70B in the cloud

Run Code Llama 70B in the cloud

Hands on with LangGraph Agent Workflows: Build a LangChain Coding Agent with Custom Tools

Hands on with LangGraph Agent Workflows: Build a LangChain Coding Agent with Custom Tools

Build an AI code generator w/ RAG to write working LangChain

Build an AI code generator w/ RAG to write working LangChain